Session by session
- Session 71 · Ask & understandWeek 36
Background changes and dataset shift
Evidence: a question, sketch or new vocabulary
- Session 72 · Build & designWeek 36
Build a second held-out condition set
Evidence: a design draft, dataset or build
- Session 73 · ImplementWeek 37
Evaluate without retraining on the test set
Evidence: a working version, explained once
- Session 74 · Test & improveWeek 37
Compare performance by condition
Evidence: a test log with at least one failure
- Session 75 · Explain & reflectWeek 38
Recommend a limited deployment setting
Evidence: an individual explanation
- P03 model
- controlled image sets
- Python/table evaluator
Twenty normal and twenty changed-condition images.
A model, an evaluation study or an AI-checking workflow.
Completion needs the artefact, an honest test log, an individual explanation and no open safety or privacy issue.
Projects in the same block
- RoboticsG08-P13
Two-Light Follower
A slow light-following model on a bounded tabletop track.
Sessions 61-65Innovation only - RoboticsG08-P14
Multi-Mode Rover
A rover with documented operating modes and safe startup.
Sessions 66-70Innovation only - AIG08-P15
Model Robustness Report
A report showing where the classifier works and where it fails.
Sessions 71-75Innovation only - IntegratedG08-P16
AI + Bluetooth Rover Showcase
A supervised rover demonstration with traceable AI decisions and manual authority.
Sessions 76-80Innovation only
For school leadersChoose a starting point.
Build from evidence.
Pick the classes and a plan. We map the timetable, kit and safety checks with you, then pilot one class first.
- Prospectus and class-wise plan
- Kit and readiness check
- Pilot one class first
- Evidence at every milestone
Let's plan your pilot.
Share a few details and we will send the right plan for your classes.